Spatial Graph Convolutional Networks

• Published in: Neural Information Processing Vol. 1333; pp. 668 - 675
• Main Authors: Danel, Tomasz, Spurek, Przemysław, Tabor, Jacek, Śmieja, Marek, Struski, Łukasz, Słowik, Agnieszka, Maziarka, Łukasz
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2020; Springer International Publishing
• Series: Communications in Computer and Information Science
• Subjects: Chemoinformatics; Convolutional neural networks; Graph convolutional networks
• ISBN: 9783030638221; 3030638227
• ISSN: 1865-0929; 1865-0937
• DOI: 10.1007/978-3-030-63823-8_76

Graph Convolutional Networks (GCNs) have recently become the primary choice for learning from graph-structured data, superseding hash fingerprints in representing chemical compounds. However, GCNs lack the ability to take into account the ordering of node neighbors, even when there is a geometric interpretation of the graph vertices that provides an order based on their spatial positions. To remedy this issue, we propose Spatial Graph Convolutional Network (SGCN) which uses spatial features to efficiently learn from graphs that can be naturally located in space. Our contribution is threefold: we propose a GCN-inspired architecture which (i) leverages node positions, (ii) is a proper generalization of both GCNs and Convolutional Neural Networks (CNNs), (iii) benefits from augmentation which further improves the performance and assures invariance with respect to the desired properties. Empirically, SGCN outperforms state-of-the-art graph-based methods on image classification and chemical tasks.